Search results

Since the introduction of the outstanding web AI chat system, ChatGPT, it has caused a significant impact in both academia and the business world. Many studies have started to explore its potential applications in various fields. However, there is a lack of research from the perspective of user experience. To fill this theoretical gap and provide a theoretical basis for the operation and design of related services, this study plans to develop a set of evaluation scales for AI chat system user experience and explore the relationship between various factors and user satisfaction.

This study obtained 41 evaluation indicators through literature review and user research. Subsequently, these indicators were used as questionnaire items, combined with satisfaction metrics. A total of 515 questionnaires were distributed, and factor analysis and linear regression were employed to determine the specific elements influencing user experience and the user satisfaction model.

This study found that the factors influencing user experience are usefulness, accuracy, logical inference, interactivity, growth, anthropomorphism, convenience, credibility, ease of use, creativity, and security. Among these factors, only accuracy, anthropomorphism, creativity, and security indirectly influence satisfaction through usefulness, while the rest of the factors have a direct positive impact on user satisfaction.

This study provides constructive suggestions for the design and operation of related services and serves as a reference for future theoretical research in this area.

The rise of interactive fitness games in the post-epidemic era has resulted in the need to establish a quality evaluation index system. This study aims to develop such a system and provide a reference for enhancing the quality of interactive fitness games.

To achieve this, interviews and questionnaires were conducted to identify the factors that influence the quality of interactive fitness games. The Kano model and SII (Satisfaction Increment Index)-Dissatisfaction Decrement Index (DDI) two-dimensional quadrant analysis were then used to explore differences in quality judgment between males and females, as well as their priorities for improving interactive fitness games.

The study revealed that males and females have different quality judgments for “rich and diverse content,” “motivational value,” “sensitive motion recognition detection” and “portability.” However, both genders share similar views on the other quality factors. In addition, the study identified differences in the priority of improvement between men and women. “Very interesting,” “effective fitness achievement,” “motivating fitness maintenance,” “sensitive motion recognition detection,” “portability” and “educational value” were found to be of higher priority for men than women.

These findings provide a valuable theoretical reference for developers and designers of interactive fitness games seeking to enhance the user experience.

Mobile e-commerce has brought convenience to consumers. But for goods such as shoes, mobile e-commerce has failed to provide the same experience as consumers would have in physical stores, and that also causes problems for online merchants, such as high return rates. As a result, the augmented reality (AR) virtual shoe-try-on function appeared. The way that AR virtual shoe-try-on study different from other AR virtual try-on studies is that AR virtual shoe-try-on study only satisfies consumers' visual experience and consumers cannot judge whether the shoes are comfort or not. Whether consumers would accept AR virtual try-on function to help them make purchase decision due to the visual experience provided by AR virtual try-on function is worth discussion. Measuring users' perceptions and preferences can help companies design AR shoe-trying functions and provide services more cost-effectively.

To promote the continuous use and better development of such mobile e-commerce based on the technology acceptance model (TAM), this study explored the influencing factors for users' intentions to continue using the AR virtual shoe-try-on function, including the perceived usefulness, perceived ease of use, system quality, perceived playfulness and attitude.

The results of this study showed that TAM is a powerful theoretical tool of the new technology in mobile e-commerce and that the system quality and perceived playfulness also have a positive impact on the original variables of TAM. System quality and perceived playfulness are important predictors of users' continuance intentions to use the AR virtual shoe-try-on function.

The main contribution of this study to model iteration and theoretical update is to verify the applicability of the TAM in the AR shoe-try-on function and to expand TAM model with system quality and perceived playfulness. The authors' results will help shoe enterprises win users' recognition through AR shoe-try-on function and improve users' continuance intention of use.

In computational chemistry, the chemical bond energy (pKa) is essential, but most pKa-related data are submerged in scientific papers, with only a few data that have been extracted by domain experts manually. The loss of scientific data does not contribute to in-depth and innovative scientific data analysis. To address this problem, this study aims to utilize natural language processing methods to extract pKa-related scientific data in chemical papers.

Based on the previous Bert-CRF model combined with dictionaries and rules to resolve the problem of a large number of unknown words of professional vocabulary, in this paper, the authors proposed an end-to-end Bert-CRF model with inputting constructed domain wordpiece tokens using text mining methods. The authors use standard high-frequency string extraction techniques to construct domain wordpiece tokens for specific domains. And in the subsequent deep learning work, domain features are added to the input.

The experiments show that the end-to-end Bert-CRF model could have a relatively good result and can be easily transferred to other domains because it reduces the requirements for experts by using automatic high-frequency wordpiece tokens extraction techniques to construct the domain wordpiece tokenization rules and then input domain features to the Bert model.

By decomposing lots of unknown words with domain feature-based wordpiece tokens, the authors manage to resolve the problem of a large amount of professional vocabulary and achieve a relatively ideal extraction result compared to the baseline model. The end-to-end model explores low-cost migration for entity and relation extraction in professional fields, reducing the requirements for experts.